Zobrazeno 1 - 3 of 3 pro vyhledávání: '"Castelli, Liam"'
1
Report
Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA
Autor: Chen, Hao Mark, Castelli, Liam, Ferianc, Martin, Zhou, Hongyu, Liu, Shuanglong, Luk, Wayne, Fan, Hongxiang
Reliable uncertainty estimation plays a crucial role in various safety-critical applications such as medical diagnosis and autonomous driving. In recent years, Bayesian neural networks (BayesNNs) have gained substantial research and industrial intere
Externí odkaz: http://arxiv.org/abs/2406.14593
Zobrazit plný text záznamu
2
Report
When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA
Autor: Fan, Hongxiang, Chen, Hao, Castelli, Liam, Que, Zhiqiang, Li, He, Long, Kenneth, Luk, Wayne
Bayesian Neural Networks (BayesNNs) have demonstrated their capability of providing calibrated prediction for safety-critical applications such as medical imaging and autonomous driving. However, the high algorithmic complexity and the poor hardware
Externí odkaz: http://arxiv.org/abs/2308.06849
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje